Breakthrough T1D Request for Applications: Artificial Intelligence Powered Approaches for T1D Cell Therapy

Funding over a maximum of three years to support research using artificial intelligence and machine learning technologies to overcome challenges in the development of next generation beta cell replacement therapies for type-1 diabetes.

Breakthrough T1D, based in the United States, is an international organisation that funds innovative research in pursuit of its mission to advance the treatment, prevention and cure of type-1 diabetes (T1D).

Breakthrough T1D has issued a Request for Applications – Artificial Intelligence Powered Approaches for T1D Cell Therapy – to solicit proposals for research projects aiming to advance the development of next generation beta cell replacement therapies for type 1 diabetes by leveraging advancements in artifical intelligence and machine learning.

One of Breakthrough T1D’s goals (as detailed in its research strategy) is to accelerate the development of therapies capable of restoring metabolic control and insulin independence in T1D through the transplantation of insulin-producing cells.

While pancreatic islet transplantation has proven efficacious in restoring metabolic control and improving quality of life in T1D patients that experience severe hypoglycemic events, there are still several major scientific and technical challenges that must be addressed before beta cell replacement can be deployed and adopted as a safe and effective therapy that is suitable for the broader T1D population.

The adverse side effects from chronic systemic immunosuppression, the limited availability of donor pancreas derived islets, poor cell survival in the post transplantation period, and the lack of biomarkers predictive of transplant health are some of the major challenges that Breakthrough T1D is seeking to enable the scientific community to address.

Breakthrough T1D has previously supported research that has achieved significant progress in overcoming several critical barriers in the development of beta cell replacement therapies (eg renewable cell sources, immune protection, and engraftment and survival). The nature of such research generates a significant volume of data which can be analysed using artificial intelligence and machine learning (AI/ML) technologies to uncover previously hidden patterns and features that can aid in the development of predictive tools and generation of new hypotheses.

While these new statistical analysis techniques have been applied to T1D research in some capacity (eg generating predictive risk scores of disease progression) they have not been widely applied to the specific barriers of beta cell replacement therapy. Accordingly, this funding opportunity aims to accelerate the pace of scientific progress and catalyse breakthroughs in the development of beta cell replacement therapies for T1D.

Breakthrough T1D is soliciting Letters of Intent aimed at addressing one or more of the following gaps in T1D cell therapy research using AI/ML:

• Improving the function and/or survival of renewable sources of insulin-producing cells (eg stem cell-derived islets).
• Developing immune protection strategies to prevent rejection of transplanted cells that do not rely on chronic systemic immunosuppression.
• Establishing methods of predicting transplanted cell survival and function prior to decline in c-peptide levels or glycaemic control.
• Implications of a specific therapeutic approach (cell type and protection strategy, site of implantation) for efficacy, safety and patient selection.

Proposals coming from multi-disciplinary teams comprised of both data scientists and expert T1D researchers will be prioritised. While applicants to this RFA do not require experience in T1D research, they are encouraged to seek collaborations with T1D experts and provide adequate evidence supporting the feasibility of the approach.

Examples of topics pertinent to this call include but are not limited to:

• Generating and analysing clinical and/or preclinical datasets to identify signatures of human beta cell stress or immune rejection to better measure and predict graft health/failure prior to decline in beta cell function or recipient’s immune status.
• Leveraging single cell datasets from other fields such as solid organ transplant or oncology to identify mechanisms capable of reducing immunogenicity or improving survival (immune checkpoint expression, vascularization, metabolism etc).
• Generating and analysing datasets on foreign body response or oxygenation requirements to understand mechanisms of tissue response at different implant sites and mitigate biomaterial rejection in cell delivery devices.
• Using large multi-well screens of small molecule libraries to identify islet or stem cell-derived islet responses that may improve transplant outcomes.